Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sharing, open source

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “open source,” i.e. references to making software or AI systems publicly available under an open‐source model.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gle
    -0.07
     copied
    -0.07
    ินเด
    -0.06
    ANS
    -0.06
     zvlá
    -0.06
     chức
    -0.06
    勝
    -0.06
    sınız
    -0.06
     essa
    -0.06
     доктор
    -0.06
    POSITIVE LOGITS
    .Serialize
    0.08
    .view
    0.07
     Logistic
    0.07
     Distrib
    0.07
     تحقیق
    0.07
    .Alignment
    0.07
    xico
    0.07
    _singular
    0.07
     Invest
    0.07
    Give
    0.06
    Act Density 0.018%

    No Known Activations